Product retrieval for grocery stores

We introduce a grocery retrieval system that maps shopping lists written in natural language into actual products in a grocery store. We have developed the system using nine months of shopping basket data from a large Finnish supermarket. To evaluate the system, we used 70 real shopping lists gathered from customers of the supermarket. Our system achieves over 80% precision for products at rank one, and the precision is around 70% for products at rank 5. Categories and Subject Descriptors H.3.3 [Information Search and Retrieval]: [Retrieval

• Type: Journal
• Year: 2008
• Where: SIGIR
• Authors: Petteri Nurmi, Eemil Lagerspetz, Wray L. Buntine, Patrik Floréen, Joonas Kukkonen
• Keywords: Information Technology, Large Finnish Supermarket, Shopping Basket Data, Shopping Lists, SIGIR 2008